Push distilbert-base-uncased trained on biored-original_splits.pt

README.md

@@ -0,0 +1,84 @@
+---
+language:
+- en
+license: mit
+base_model: distilbert-base-uncased
+tags:
+- low-resource NER
+- token_classification
+- biomedicine
+- medical NER
+- generated_from_trainer
+datasets:
+- medicine
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: Dagobert42/distilbert-base-uncased-biored-finetuned
+ results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Dagobert42/distilbert-base-uncased-biored-finetuned
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the bigbio/biored dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6976
+- Accuracy: 0.7703
+- Precision: 0.5335
+- Recall: 0.424
+- F1: 0.4652
+- Weighted F1: 0.7512
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------:|
+| No log | 1.0 | 25 | 0.9181 | 0.7144 | 0.4183 | 0.1593 | 0.151 | 0.6108 |
+| No log | 2.0 | 50 | 0.8580 | 0.7283 | 0.5273 | 0.2252 | 0.2508 | 0.6404 |
+| No log | 3.0 | 75 | 0.8232 | 0.7369 | 0.5603 | 0.2769 | 0.3173 | 0.6638 |
+| No log | 4.0 | 100 | 0.7814 | 0.7476 | 0.5184 | 0.3618 | 0.4085 | 0.7031 |
+| No log | 5.0 | 125 | 0.7691 | 0.7507 | 0.5306 | 0.3929 | 0.4283 | 0.7173 |
+| No log | 6.0 | 150 | 0.7492 | 0.7607 | 0.5494 | 0.3919 | 0.4396 | 0.7244 |
+| No log | 7.0 | 175 | 0.7616 | 0.7622 | 0.5553 | 0.4048 | 0.4481 | 0.728 |
+| No log | 8.0 | 200 | 0.7256 | 0.7657 | 0.5437 | 0.4306 | 0.4717 | 0.7426 |
+| No log | 9.0 | 225 | 0.7413 | 0.7684 | 0.5565 | 0.4315 | 0.4739 | 0.7422 |
+| No log | 10.0 | 250 | 0.7497 | 0.7721 | 0.5606 | 0.4364 | 0.4789 | 0.7446 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,42 @@
+{
+ "_name_or_path": "distilbert-base-uncased",
+ "activation": "gelu",
+ "architectures": [
+ "DistilBertForTokenClassification"
+ ],
+ "attention_dropout": 0.1,
+ "dim": 768,
+ "dropout": 0.1,
+ "hidden_dim": 3072,
+ "id2label": {
+ "0": "null",
+ "1": "GeneOrGeneProduct",
+ "2": "DiseaseOrPhenotypicFeature",
+ "3": "ChemicalEntity",
+ "4": "OrganismTaxon",
+ "5": "SequenceVariant",
+ "6": "CellLine"
+ },
+ "initializer_range": 0.02,
+ "label2id": {
+ "CellLine": 6,
+ "ChemicalEntity": 3,
+ "DiseaseOrPhenotypicFeature": 2,
+ "GeneOrGeneProduct": 1,
+ "OrganismTaxon": 4,
+ "SequenceVariant": 5,
+ "null": 0
+ },
+ "max_position_embeddings": 512,
+ "model_type": "distilbert",
+ "n_heads": 12,
+ "n_layers": 6,
+ "pad_token_id": 0,
+ "qa_dropout": 0.1,
+ "seq_classif_dropout": 0.2,
+ "sinusoidal_pos_embds": false,
+ "tie_weights_": true,
+ "torch_dtype": "float32",
+ "transformers_version": "4.35.2",
+ "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b77f92470c32771073dc6fedf9dbaacabb338a841291109a831d0eaffcb1d5
+size 265485396

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+ "cls_token": "[CLS]",
+ "mask_token": "[MASK]",
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "100": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "101": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "102": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "103": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_lower_case": true,
+ "mask_token": "[MASK]",
+ "model_max_length": 512,
+ "pad_token": "[PAD]",
+ "sep_token": "[SEP]",
+ "strip_accents": null,
+ "tokenize_chinese_chars": true,
+ "tokenizer_class": "DistilBertTokenizer",
+ "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1eac4aea06037b9c3183adcbf333a38e173e27a040d33ef7a4a7a2239a5e1a4
+size 4219